Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations already declaring readOnlyHint=false and destructiveHint=false, the description adds meaningful context beyond them: plan_apply 'applies it as one undoable edit', prepare 'queues source sampling' (async), plan_save validates observations against sampled frame times, and it discloses account-tier export limits (3 badged 720p exports free, 2 clean/day trials, unlimited subscribers). Concurrency/idempotency semantics of expectedRevision and idempotencyKey remain unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Information density is high and the action list is front-loaded, but it is delivered as one dense paragraph mixing parameter lists, tier limits, and version notes, which makes it hard to scan. Little structural separation between the six actions despite each being a distinct entry point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-action, 23-parameter tool with no output schema, the description covers the action set, the plan lifecycle, undoability, and tier gating, and points to video_guide for exact schemas. It is largely self-sufficient, though the missing concurrency/idempotency explanation leaves a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% across 23 params, so the description carries the burden, and it does substantial work by grouping parameters per action (which params belong to prepare vs captions vs direction) since one schema serves six actions. It also clarifies sub-structures ('words[] with text/startFrame/endFrame', 'kitId from video_strategies action=directions, or level+seed'). It stops short of explaining expectedRevision or idempotencyKey semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific tool ('Video Director producer') and enumerates six concrete actions (prepare, plan_save, plan_apply, cancel, captions, direction) with their parameters, so the agent knows exactly what resource it manages. It even cross-references sibling tools (video_guide, video_strategies action=directions) for context. It stops short of explicitly distinguishing itself from close siblings like video_producer_status or video_edit_apply.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one explicit prerequisite ('Call video_guide first for the catalog, the exact input schema of each action and this account's tier notes') and implies the prepare→plan_save→plan_apply sequence through action ordering. However, it never says when to pick this tool over video_edit_apply, video_render, or video_producer_status, and gives no when-not guidance. Usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.